EP3038053B1 - Procédé et système de génération de données de modèle de vêtement - Google Patents

Procédé et système de génération de données de modèle de vêtement Download PDF

Info

Publication number
EP3038053B1
EP3038053B1 EP14199802.1A EP14199802A EP3038053B1 EP 3038053 B1 EP3038053 B1 EP 3038053B1 EP 14199802 A EP14199802 A EP 14199802A EP 3038053 B1 EP3038053 B1 EP 3038053B1
Authority
EP
European Patent Office
Prior art keywords
garment
image data
model
shape
piece
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP14199802.1A
Other languages
German (de)
English (en)
Other versions
EP3038053A1 (fr
Inventor
Stefan Hauswiesner
Philipp Grasmug
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Reactive Reality AG
Original Assignee
Reactive Reality AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Reactive Reality AG filed Critical Reactive Reality AG
Priority to ES14199802T priority Critical patent/ES2765277T3/es
Priority to EP14199802.1A priority patent/EP3038053B1/fr
Priority to PCT/EP2015/079633 priority patent/WO2016102228A1/fr
Priority to US15/535,942 priority patent/US10380794B2/en
Publication of EP3038053A1 publication Critical patent/EP3038053A1/fr
Application granted granted Critical
Publication of EP3038053B1 publication Critical patent/EP3038053B1/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20116—Active contour; Active surface; Snakes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/16—Cloth
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling

Definitions

  • the present invention relates to a method for generating garment model data representative of a piece of garment, to a system for generating such garment model data and to a computer program product implementing such a method.
  • An object to be achieved is to provide an improved concept for generating garment model data that is more flexible with respect to the source or type of input image data.
  • the improved concept is based on the idea of processing input image data containing a view of the piece of garment to be modelled such that a wearing condition is determined in a first step. For example, it can be distinguished whether the input image data represent a garment that is worn by a person or that is not worn. Based on this differentiation a specific further processing of the input image data is performed. For example, if the piece of garment is determined to be worn, the processing is performed by finding contours of the piece of garment based on a pre-set body model in conjunction with a garment template model retrieved from a garment template model database. In the not worn condition a matching garment template model is determined from the database and used for aligning contours of the garment image with the garment template model.
  • the shapes that result from the processing can be used to determine the garment model data which then can be used flexibly with any kind of user photos or, if desired, avatars.
  • the improved concept allows the use of a broader spectrum of image types, which do not require, e.g., photo studio conditions or other artificial limitations.
  • the garment template model database preferably is created in a pre-processing step and contains a small set of garment data for each garment category.
  • Garment categories can conform to garment types, such as sweaters, pants, dresses etc. but also to different variants of the same type, such as maxi dresses or long-sleeved shirts.
  • the garment template model database contains only a subset of available garments.
  • each garment template model stored in the database preferably contains a different amount of information with respect to an exact representation of a piece of garment.
  • a method for generating garment model data representative of a piece of garment comprises processing input image data containing a view of the piece of garment as defined in appended claim 1.
  • the input image data may be picked from a website through a browser or via a computer application or a smartphone application.
  • the input image data can also result from photographs taken by a user.
  • the user takes a photo of a person wearing the garment or of the garment lying on the floor, hanging on a clothes hanger, worn by a display dummy or mannequin or the like.
  • the improved concept is independent of support of a clothes retailer and does not require special hardware like sensors, marker suits etc.
  • no special skills are required for use, such as modelling, photo editing, aligning or arranging things. Users can also take photographs, scans or screenshots of other media like catalogues, magazines or screens.
  • a body model is aligned with the image of the garment to drape the garment onto a user's body later on.
  • each of the garment template models stored in the garment template model database contains one or more of the following: a set of control points that define a relationship between a shape of a garment and a body wearing said garment, a geometrical description that defines a relationship between a shape of a garment and a body wearing said garment, metadata associated with a shape of a garment, metadata associated with the type of a garment, metadata associated with fitting information of a garment.
  • a garment template model may feature a defined number of such control points, wherein at least some of the control points are associated with predefined body parts such as shoulders, hips, ankles, elbows or the like. If no control points are used, or in addition, the geometrical description mentioned above can fulfil the same purpose.
  • Metadata contained by the garment template models may define a basic shape or type of the garment, making e.g. a matching process with an input image faster and/or more reliable. This is particularly the case if the input image data also contain metadata, e.g. provided by the user or obtained from a website or the like. However, such metadata are not mandatory.
  • the fitting information may be information on which garments or garment parts fit a body tightly and which fit loosely.
  • adapting the identified shapes may comprise aligning control points contained in the garment template model with corresponding points of the shape of the piece of garment and of the shape of the person.
  • the aligning may also be done based on a geometrical description contained in the garment template model, such that a geometrical description of the shape of the piece of garment and of the shape of the person is aligned.
  • control points and/or geometrical description may be determined on the pre-set body model from the input image data, defining e.g. head, shoulders, arms, legs and the like in conjunction with the aligning of the control points and/or geometrical description of the garment template model associated with the corresponding body parts. Consequently, e.g. both the garment worn by the person and a body of the person are finally found or set in the input image data. Due to the support with the garment template model, this can also be called an extended active contour modelling approach.
  • determining the garment model data comprises separating background image data and body image data, which show parts of the person not being covered by the piece of garment, from the input image data to obtain garment image data.
  • the separating is based on the adapted identified shapes and on colour identification in the input image data. Accordingly, a segmentation of the input image data based on the identified shapes is performed in order to retrieve only those parts of the image showing the piece of garment.
  • determining the garment model data may further comprise identifying regions in the garment image data which are occluded, and substituting such identified regions with matching image data.
  • the identifying and/or the substituting can be based on a garment template model retrieved from the garment template model database.
  • the garment template model may be the same as that used during adaptation of the identified shapes or may be a different garment template model that fits better after segmentation of the piece of garment. For example, occluded parts, e.g. by a hand of a user, may disturb a continuous shape of the piece of garment, which is corrected with the part of the garment template model that provides a corrected shape. Previously occluded image regions may then be refilled with e.g. image pattern of the original input image data. Of course, if no occluded regions are present and therefore not identified, no substituting is performed.
  • identifying the matching garment template model may comprise an iterative determination of a similarity metric between the respective garment template model and the input image data and/or the identified shape.
  • the selection of the matching garment template model is based on the iteratively determined similarity metric.
  • a similarity metric may be one or more values that are calculated by comparing single or multiple features of the original input image data and the garment template model. For example, such a comparison may include comparison of shapes, control points, dimensions, geometrical descriptions or the like.
  • the selection may be based on an evaluation of the similarity metric by e.g. calculating a total matching factor from the similarity metric and taking the garment template model with the highest matching factor.
  • aligning the identified shape may comprise aligning control points and/or a geometrical description contained in a matching garment template model with corresponding points of the shape of the piece of garment.
  • the control points and/or a geometrical description of the template model preferably are identified before in an initial step.
  • a popular presentation format is to drape the garment on a mannequin. In that case, the mannequin needs to be removed for virtual try-on.
  • Some online shops edit the images such that the mannequin becomes invisible and the back side of the garment can be seen.
  • Some users may opt to lay the clothes on the ground or put them on a hanger for taking pictures. In the latter cases, the backside of the garment needs to be removed. For the last case, the hanger needs to be removed as well.
  • determining the garment model data may comprise obtaining garment image data associated with the piece of garment from the input image data based on the aligned identified shapes. Furthermore, the determination of the garment model data comprises identifying at least one region in the garment image data that would not be visible, if the piece of garment was worn by a person, and excluding such an identified region from the garment image data and the garment model data. For example, a frontal image of a shirt with a neckline usually also includes part of the back side of the shirt, which is not visible when the shirt is worn by a person. Hence, such a region can be excluded in the output garment model data. However, if no such regions can be identified, e.g. because they are simply not present, no exclusion is performed in consequence.
  • the identification of such a region comprises a determination of image gradients in the garment image data, comparing the image gradients to a set of geometrical shapes to achieve a matching quantity for each of the geometrical shapes, selecting one of the geometrical shapes based on the matching quantities, and defining the at least one region based on the selected geometrical shape.
  • a plurality of ellipse equations with different parameters define the set of geometrical shapes that are compared to the image gradients of the input image data.
  • a single equation may be sufficient to define such an edge, whereas in other situations two or more equations may be necessary for defining the shape of the region.
  • the number and type of equations can be made dependent on the type of garment, for example.
  • the determination of the garment model data may further comprise, if the piece of garment includes a sleeve or a pant leg, identifying a first and a second point along the sleeve or the pant leg, respectively. Furthermore, image gradients are determined in the input image data, and the image gradients are compared to a set of interconnection paths between the first and the second point to achieve a matching quantity for each of the interconnection paths. One of the interconnection paths is selected based on the matching quantities to be used as separation information in the garment model data.
  • the process of generating garment model data may be performed based on conventional images showing a two-dimensional representation of the piece of garment.
  • the conventional images may be still images or single images from a video sequence.
  • the output garment model data may also be representative of a two-dimensional view of the piece of garment.
  • the garment model data are generated such that they contain depth information and/or three-dimensional information.
  • the input image data containing a view of the piece of garment may already contain depth information or three-dimensional information, which may be generated in a special imaging process using, e.g. infrared imaging techniques or other 3D imaging techniques known in the art.
  • the input image data may also be provided as a two-dimensional or three-dimensional video sequence or animation, from which the depth information or three-dimensional information may be extracted.
  • the processing may be performed in three dimensions such that the resulting garment model data contain a three-dimensional representation of the piece of garment.
  • the garment template models stored in the garment template model database may contain three-dimensional and/or depths information which is aligned and/or adapted to the shapes in the input image data. This also works if the input image data are two-dimensional. For example, the garment image data may be enhanced with the three-dimensional or depth information from the garment template model.
  • the determination of the type of wearing condition may be performed based on one or more factors associated with the input image data.
  • bases are a face detection, a body detection, a body part detection, when for example no full body is visible, a detection of skin regions like hands, arms, legs or feet, a hair detection or a garment recognition.
  • the determination can be based on a wearing condition indicated in metadata comprised by the input image data.
  • the retrieval of garment template models from the garment template model database may be based on additional information that may be comprised by the input image data.
  • a type of garment can be indicated in metadata comprised by the input image data.
  • a shooting condition may be indicated in metadata comprised by the input image data.
  • such a shooting condition may indicate whether the piece of garment is lying on the floor, hanging on a clothing hanger or the like.
  • a shooting angle may be indicated in metadata comprised by the input image data. For example, if a piece of garment which is lying on the floor or on a bed or the like is photographed with a mobile phone including a position, orientation and/or acceleration sensor, the shooting angle provided by the respective sensor may indicate that the photo was taken in a downward direction.
  • the various embodiments and implementations described above for performing the generation of garment model data according to the improved concept may be implemented in a system, in particular in a computer system.
  • a system comprises a processor that is configured for executing the various processing steps described above.
  • a system may be integrated in a mobile phone, a tablet computer, a notebook or a desktop computer or similar equipment.
  • the garment template model database may be stored on the system or device, respectively, or stored on a remote computer which is accessed over a remote connection, e.g. a network connection.
  • the improved concept may also be implemented in software or as a computer program product comprising respective program code. Implementation may be performed on a digital storage medium, in particular a disk or a CD having electronically readable control signals that may cooperate with a programmable computer system such that the corresponding method is performed.
  • a solution according to the improved concept thus also consists in a computer program product having a program code, stored on a machine-readable carrier, for performing the method according to the improved concept, when the computer program product runs on a computer.
  • FIG. 1 shows an example flowchart of a virtual try-on session 100.
  • a composited image may be created that shows a user wearing selected clothes or garments.
  • the inputs of such a virtual try-on session are garment image data 110 and user image data 120.
  • image data 110, 120 may include photos of the piece of garment to be virtually worn by the user and photos of the user.
  • the garment image data and/or the user image data may comprise photos or images of a piece of garment, respectively the user, and additional information related to the image.
  • Garment images can be picked from a website, e.g. using a specific browser plugin, or using a specific application. It is also possible to use garment images photographed by the user.
  • the example session 100 starts with two separate process chains for the garment image and the user photo that converge in a merging step and several post-processing steps.
  • a garment model represented by garment model data is generated from the garment image data.
  • user data may be modelled in block 130 from the user image data 120.
  • the garment model data are combined with the user data.
  • a body model of the user's photo is aligned with the garment model data in order to adapt the garment's shape and pose to that of the user data. This may be done by computing necessary rigid and non-rigid transformations, e.g. by employing a variant of Laplacian mesh editing.
  • a colour adaptation is performed. This may be necessary if the quality of the user photo and the garment photo differ, e.g. by contrast, saturation or brightness. Accordingly, the better quality photo may be adapted to the lower quality photo, or vice versa. Additionally, lighting of a garment image can be adapted to the lighting of the user image. This may be achieved by subtracting the lighting of the garment scene and adding the lighting of the user scene.
  • the composited image showing the user with the piece of garment can be displayed in block 160.
  • the result may either be a still image or a sequence of images showing an animation of the try-on computation.
  • Result images can be shown in an overlay of an existing website, embedded in an existing website, possibly replacing original content.
  • Results can also be shown on a personal website of the user, in social network applications, or attached to mails etc.
  • the results can be shown on the display of a mobile device like a smartphone or tablet, preferably within a mobile application implementing the improved concept.
  • FIG. 2 shows an example flowchart of the process 200 of generating garment model data representative of a piece of garment according to the improved concept.
  • all types of garment images in particular frontal garment images, can be processed.
  • the images or photos can be with or without a human model or a mannequin, can lie on the floor, on a clothing hanger or the like.
  • the garment model data generation process is independent of support of a retailer of the clothing. Furthermore, it does not require special hardware such as sensors, marker suits or the like. Additionally, no special skills like modelling, photo editing, aligning or arranging things are necessary.
  • the improved concept it is distinguished between at least two major types of fashion images, as indicated by decision block 210.
  • the first type contains pictures of people wearing clothes, such as models or users or even full-sized mannequins.
  • the second type contains garments that are not worn by anyone, such as garments on a hanger.
  • the garment images to be analysed, included in the garment image data 110 may be picked up from a website or be taken by the user from real pieces of garment or clothes.
  • photographs, scans or screenshots of other media like catalogue, magazine or screens can be provided.
  • a type of wearing condition is determined from the input image data as at least one of a first type, where the piece of garment is worn by a person, and of a second type, where the piece of garment is not worn.
  • Such determination of the type of wearing condition may be performed based on various decision sources. For example, a face detection, a body detection, a body part detection, a detection of skin regions or a hair detection, may be used.
  • the garment image data 110 may comprise metadata that indicate the type of wearing condition in advance.
  • processing block 220 where an active contour modelling is performed.
  • the body of the model or a user can be used to estimate the garment's scale and fit.
  • statistical body models usually describe human bodies in an undressed state. If, for example, the garment does not fit tightly to the user's body, as a consequence a standard active contour modelling approach may have difficulties in detecting, for example, the legs of the model when a dress is worn.
  • Figure 3A shows a model wearing a dress.
  • Figure 3B shows a standard active contour modelling approach on the basis of the image of Figure 3A , which results in that the body under the dress is not properly estimated.
  • an extended active contour modelling approach is used. It may be initialized with a face detector and a statistical body model. For example, in processing block 220 a shape of the piece of garment and a shape of the person wearing the piece of garment are identified in the input image data utilizing the active contour modelling approach based on a pre-set body model, e.g. the statistical body model.
  • the identified shapes are adapted based on a garment template model retrieved from a garment template model database 240.
  • retrieving the garment template model from the garment template model database 240 is based on a type of garment indicated in metadata comprised by the input image data.
  • the retrieval can also be based on garment recognition.
  • the garment template database 240 may be created in a pre-processing step. It can contain a small set of garment images for each garment category. Garment categories can conform to garment types, like sweaters, pants, dresses or the like, but also to different variants of the same type like maxi dresses or long-sleeved shirts.
  • processing block 230 it may be returned to processing block 220 with the adapted identified shapes for improving the active contour modelling.
  • the contours of a garment follow the deformations of the underlying body model, for example by a skeleton animation approach.
  • deformations relative to the model like skirt length, sleeve length, tightness, may be considered by the contour modelling algorithm.
  • one or more templates from the garment template database may be adapted to the image.
  • a matching value can be calculated for each of the garment template models, including both matching of the body shape and the garment shape.
  • the garment template models with the best matching value are taken for further processing in processing block 250.
  • Figure 3C shows an example result of the improved concept, where both body and garment shape are correctly estimated.
  • the body shape is indicated by the solid line, as in Figure 3B
  • the garment shape is indicated by the dashed line.
  • the process of generating garment model data may be performed based on conventional images showing a two-dimensional representation of the piece of garment.
  • the garment model data are generated such that they contain depth information and/or three-dimensional information.
  • the input image data containing a view of the piece of garment may already contain depth information or three-dimensional information, which may be generated in a special imaging process using, e.g. infrared imaging techniques or other 3D imaging techniques known in the art.
  • the body model can be a three-dimensional surface model, e.g. a mesh, that is aligned with the depth samples of the input image.
  • the body model may be a two-dimensional body pose and shape model that can be used to describe the silhouette or shape of the user.
  • the garment template models stored in the garment template model database may contain three-dimensional and/or depth information which is aligned and/or adapted to the shapes in the input image data. This also works if the input image data are two-dimensional. For example, the garment image data may be enhanced with the three-dimensional or depth information from the garment template model.
  • a segmentation of the input image data is performed.
  • the garment model data are determined from the input image data based on the adapted identified shapes from processing blocks 220 and 230.
  • Each of the garment template models stored in the garment template model database 240 may contain a set of control points that define a relationship between a shape of a garment and a body wearing said garment. It is also a possible implementation that each of the garment template models contains a geometrical description defining such relationship. Other information contained in a garment template model may be metadata associated with a shape of a garment and/or with a type of a garment. Of course, each garment template model can contain a combination of the information described above and also additional information.
  • adapting the identified shapes in processing blocks 220 and 230 may comprise aligning control points contained in the garment template model with corresponding points of the shape of the piece of garment and of the shape of the person.
  • control points may for example relate to specific body parts or body positions such as shoulders, arms, hips, legs or the like.
  • the image data corresponding to the piece of garment may be separated from the input image data based on the identified shapes. For example, background and body parts are removed from the input image data to have image data for the resulting garment model data.
  • a statistical model of the skin colour of the model is computed from a face region in the image data.
  • a colour model of the garment can also be computed.
  • the image data may be labelled according to the similarity with the colour models.
  • a second label map can be computed that reflects likely garment positions. For example, it is assumed that pants are usually not found in the upper body half.
  • pixels may be classified as garment and non-garment. All non-garment pixels are to be replaced later with the user's photo as described above in conjunction with block 140 of Figure 1 .
  • determining the garment model data in processing block 250 may comprise separating background image data and body image data, which show parts of the person not being covered by the piece of garment, from the input image data to obtain garment image data. As described before, the separating is based on the adapted identified shapes and on colour identification in the input image data.
  • the processing in segmentation block 250 may be finished, resulting in the final garment model data 280. However, if parts of the garment are overlapping or occluded, further processing may be necessary.
  • garment image data are shown which are, for example, based on the original image data of Figure 3A where body parts such as head, legs and hands are removed.
  • the segmentation process in block 250 of Figure 2 may further comprise identifying regions in the garment image data which are occluded, and substituting such identified regions with matching image data.
  • the identifying and/or the substituting may be based on a garment template model retrieved from the garment template model database 240.
  • the sleeves of the dress are separated from their original position using the information of a garment template model.
  • This can be the same as used in the shape identification adaptation process, but can also be another garment template model retrieved from the garment template model database 250.
  • the occluded parts are still present and are preferably filled in with a matching pattern.
  • the result of such an operation is shown as an example in Figure 4C .
  • the most probable shape of the garment is, for example, taken from the garment template model.
  • a similar garment is to be found.
  • a shape of the piece of garment is identified in the input image data.
  • the input image data is iteratively compared with a respective garment template model retrieved from the garment template model database 240 to identify a matching garment template model.
  • a similarity metric is iteratively determined between the respective garment template model and the input image data and/or the identified shape.
  • the matching garment template model may be selected based on the iteratively determined similarity metric.
  • FIG. 5 an example flowchart of the process of processing block 260 is shown.
  • the garment image data denoted by numeral 510
  • the image data and/or the shape of the trousers are presented, representative of an example pair of trousers.
  • various garment template models for such trousers in processing block 520.
  • information about the garment category, silhouettes, segmentation masks or other image features can be used.
  • the most similar garment template model is then automatically aligned to the shape of the piece of garment identified before.
  • the most similar garment template models are aligned to the shape of the piece of garment identified before.
  • the alignment process is, for example, shown in block 530.
  • This procedure can use non-rigid image alignment on the silhouette images.
  • control points of the garment template model may be morphed according to such image alignment operation.
  • a well-fitting garment model can be obtained for a given garment input image data.
  • the result of the aligning is shown as an example in step 550.
  • FIG. 6A and Figure 6B image data of a dress not worn by a person is shown.
  • the garment image data are shown as originally presented.
  • a human body model is additionally depicted, representing the information retrieved from the garment template model database for this kind of garment.
  • the shape of the garment is included in the output garment model data but also the relationship to the human body, which for example may be needed in a later virtual try-on process, as described for example for Figure 1 .
  • a segmentation of the input image data can be performed based on the identified shape and on results of the aligning in order to determine the garment model data in processing block 280.
  • aligning the identified shape may comprise aligning control points contained in a matching garment template model with corresponding points of the shape of the piece of garment.
  • determining the garment model data may comprise obtaining garment image data associated with the piece of garment from the input image data based on the aligned identified shapes and further comprises identifying at least one region in the garment image data that would not be visible if the piece of garment was worn by a person. Such identified regions are excluded from the garment image data and the garment model data. If no such regions can be identified, e.g. because they are simply not present, no exclusion is performed in consequence.
  • the identification of such a region may be performed by determining image gradients in the garment image data and comparing these image gradients to a set of geometrical shapes to achieve a matching quantity for each of the geometrical shapes. Finally, one of the geometrical shapes is selected based on the matching quantities and used for defining the at least one region.
  • Such geometrical shapes may be ellipses or lines or other geometrical forms that are varied with a number of parameters.
  • image data representing the upper part of a dress is shown, wherein the light dotted area is a back side or inner side of the dress.
  • the original input image data, or at least a part of it are shown, whereas in the lower part of Figure 7A an ellipse is included defining the border of region to be excluded.
  • a coincidence of the shape with an image gradient along the shape is calculated.
  • an image gradient a determination of which is well known in the art, has significant values if there are transitions between regions of different brightness or the like.
  • the shape having the highest coincidence with the image gradient is chosen for the definition of the region.
  • FIG. 7D A further example of such region identification is shown in Figure 7D , representing a top with a visible back side in the neckline region.
  • the region can be defined by a set of geometrical shapes.
  • two ellipse equations are employed to define the shape, respectively the region.
  • Figure 7C shows a further example, wherein a back side of a smoking or dinner jacket is removed based on the same principle.
  • the comparison between the geometrical shapes and the image gradients can be limited to specific regions of the garment image data. For example, it may be a generally good assumption to search for regions to be excluded in the upper part of the image. Different approaches may be necessary for some types of garments. Hence, such region identification may further be based on the type of garment being identified.
  • sleeves or pant legs may be close to each other or other body parts.
  • transformation of such garment parts may become difficult during a non-rigid image registration process if an independent transformation is desired.
  • Figure 8A Such an image situation is, for example, shown in Figure 8A where the sleeves of a sweatshirt are close to the body part of the sweatshirt itself.
  • a first and a second point along the sleeve or the pant leg can be identified, which preferably can be detected reliably such as an armpit or crotch or a point close to the hip or ankle.
  • the first and the second point lie on the garment's silhouette.
  • several cut hypotheses are evaluated by matching them with garment image gradients. For example, such image gradients are determined in the input image data and are compared to a set of interconnection paths between the first and the second point to achieve a matching quantity for each of the interconnection paths.
  • FIG. 8B An example for such interconnection paths and the selection of the first and the second point is, for example, shown in Figure 8B , where the first point is in the armpit and the second point is close to the hip.
  • one of the interconnection paths is selected as separation information in the garment model data.
  • the best cut or separation is executed by inserting background pixels or passing such information with the garment model data. The result is that the sleeves or pant legs to not stick to other parts during non-rigid image registration, which enables a more realistic try-on result.
  • Figure 8C a separated version of the image of Figure 8A is shown in Figure 8C .
  • the photo may contain a perspective distortion resulting e.g. from an angle in which the photograph is taken.
  • Such perspective distortion of the photo may be compensated if information is present that allows determination of the grade of perspective distortion. For example, if a door, a doorframe, a screen frame, a rectangular catalogue outline or the like is present in the input image data, respective lines can be detected to form a rectangle in the image, the detection for example being based on a Hough transform. If a rectangle was found, the four angles may be used to determine a perspective homography for unwarping the image. Additionally or as an alternative, a shooting angle of the photograph taken may be evaluated, wherein such shooting angle may be provided by a position, orientation or acceleration sensor in a camera or smartphone.
  • the garment model data may contain a set of control points or a geometrical description that define a relationship between a shape of the garment and a body wearing said garment. Such information can later on be used when the garment model data are combined with the user image data, as is described before for block 140 of Figure 1 .
  • FIG 9A an example of garment model data with an underlying body model, denoted by a solid line, is shown. This basically corresponds to the image shown in Figure 6B . However, additionally in Figure 9A a dashed outline of a user body is shown, having slightly different leg and arm positions.
  • the body model of the garment model data can be aligned with the shape of the user, which can be used as a basis for image transformation.
  • Figure 9C shows the result where also the garment image data are transformed by rigid and non-rigid transformations to match with the user's body.
  • a variant of Laplacian mesh editing is used in this case.
  • image data which may be more difficult to classify. For example, if a piece of garment like a dress is worn by a full body mannequin being visible in the input image data, such an image may be determined as being of the first type where the garment is worn.
  • image data of garment worn by a person but missing significant body parts may be determined as the second type of garment not worn. For example, if the head or legs are not included in the input image data, such images may also be processed as the second type. More generally speaking, input images which include a relationship between a body model and the piece of garment may be categorized as the first type. Accordingly, images which do not inherently provide a relationship between the piece of garment and the underlying body model may be categorized as the second type.
  • Figure 10 is a block diagram of a computer system that may incorporate embodiments according to the improved concept.
  • Figure 10 is merely illustrative of an embodiment incorporating the improved concept and does not limit the scope of the invention as recited in the claims.
  • One of ordinary skill in the art would recognize other variations, modifications, and alternatives.
  • computer system 700 typically includes a monitor 710, a computer 720, user output devices 730, user input devices 740, communications interface 750, and the like.
  • computer 720 may include a processor(s) 760 that communicates with a number of peripheral devices via a bus subsystem 790.
  • peripheral devices may include user output devices 730, user input devices 740, communications interface 750, and a storage subsystem, such as random access memory (RAM) 770 and disk drive 780.
  • RAM random access memory
  • User input devices 730 include all possible types of devices and mechanisms for inputting information to computer system 720. These may include a keyboard, a keypad, a touch screen incorporated into the display, audio input devices such as voice recognition systems, microphones, and other types of input devices. In various embodiments, user input devices 730 are typically embodied as a computer mouse, a trackball, a track pad, a joystick, wireless remote, drawing tablet, voice command system, eye tracking system, and the like. User input devices 730 typically allow a user to select objects, icons, text and the like that appear on the monitor 710 via a command such as a click of a button or the like. User input devices 730 may also include color and/or depth cameras, body shape and/or pose tracking sensors, hand tracking devices, head tracking devices or the like.
  • User output devices 740 include all possible types of devices and mechanisms for outputting information from computer 720. These may include a display (e.g., monitor 710), non-visual displays such as audio output devices, etc.
  • Communications interface 750 provides an interface to other communication networks and devices. Communications interface 750 may serve as an interface for receiving data from and transmitting data to other systems.
  • Embodiments of communications interface 750 typically include an Ethernet card, a modem (telephone, satellite, cable, ISDN), (asynchronous) digital subscriber line (DSL) unit, FireWire interface, USB interface, and the like.
  • communications interface 750 may be coupled to a computer network, to a FireWire bus, or the like.
  • communications interfaces 750 may be physically integrated on the motherboard of computer 720, and may be a software program, such as soft DSL, or the like.
  • computer system 700 may also include software that enables communications over a network such as the HTTP, TCP/IP, RTP/RTSP protocols, and the like.
  • RAM 770 and disk drive 780 are examples of tangible media configured to store data, including executable computer code, human readable code, or the like. Other types of tangible media include floppy disks, removable hard disks, optical storage media such as CD-ROMS, DVDs and bar codes, semiconductor memories such as flash memories, read-only-memories (ROMS), battery-backed volatile memories, networked storage devices, and the like. RAM 770 and disk drive 780 may be configured to store the basic programming and data constructs that provide the functionality of the improved concept.
  • RAM 770 and disk drive 780 Software code modules and instructions that provide the functionality of the improved concept may be stored in RAM 770 and disk drive 780. These software modules may be executed by processor(s) 760. RAM 770 and disk drive 780 may also provide a repository for storing data used in accordance with the present invention.
  • RAM 770 and disk drive 780 may include a number of memories including a main random access memory (RAM) for storage of instructions and data during program execution and a read only memory (ROM) in which fixed instructions are stored.
  • RAM 770 and disk drive 780 may include a file storage subsystem providing persistent (non-volatile) storage for program and data files.
  • RAM 770 and disk drive 780 may also include removable storage systems, such as removable flash memory.
  • Bus subsystem 790 provides a mechanism for letting the various components and subsystems of computer 720 communicate with each other as intended. Although bus subsystem 790 is shown schematically as a single bus, alternative embodiments of the bus subsystem may utilize multiple busses.
  • Figure 10 is representative of a computer system capable of embodying the improved concept. It will be readily apparent to one of ordinary skill in the art that many other hardware and software configurations are suitable for such use.
  • the computer may be a mobile device, in particular a mobile phone, or desktop, portable, rack-mounted or tablet configuration. Additionally, the computer may be a series of networked computers.
  • Various embodiments of the improved concept can be implemented in the form of logic in software or hardware or a combination of both.
  • the logic may be stored in a computer readable or machine-readable storage medium as a set of instructions adapted to direct a processor of a computer system to perform a set of steps disclosed in embodiments of the improved concept.
  • the logic may form part of a computer program product adapted to direct an information-processing device to automatically perform a set of steps disclosed in embodiments of the improved concept.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Image Analysis (AREA)
  • Processing Or Creating Images (AREA)

Claims (15)

  1. Procédé pour générer des données de modèle de vêtement représentatives d'une pièce de vêtement, le procédé comprenant
    - traiter les données d'image d'entrée contenant une vue du vêtement ;
    - déterminer un type d'état de port à partir des données d'image d'entrée comme étant au moins l'un d'un premier type, où le vêtement est porté par une personne, et d'un second type, où le vêtement n'est pas porté ;
    - si le premier type est déterminé,
    -- identifier une forme de la pièce de vêtement et une forme de la personne portant la pièce de vêtement dans les données d'image d'entrée en utilisant une approche de modélisation de contour active basée sur un modèle de corps prédéfini, dans lequel l'approche de modélisation de contour active est initialisée avec un détecteur de visage et le modèle de corps prédéfini, qui est notamment un modèle statistique du corps ;
    -- adapter la forme identifiée de la pièce de vêtement et la forme identifiée de la personne, à partir d'un motif de modèle de vêtement extrait d'une base de données de motifs de modèle de vêtement ; et
    -- déterminer les données du modèle de vêtement à partir des données d'image d'entrée en se basant sur les formes identifiées adaptées ; et
    - si le deuxième type est déterminé,
    -- identifier une forme du vêtement dans les données de l'image d'entrée ;
    -- comparer de façon itérative les données d'image d'entrée avec un motif de modèle de vêtement respectif extrait de la base de données du motifs de modèle de vêtement pour identifier au moins un modèle de vêtement correspondant ;
    -- aligner la forme identifiée avec une forme d'au moins un motif de modèle de vêtement correspondant ; et
    -- déterminer les données du modèle de vêtement à partir des données d'image d'entrée en fonction de la forme identifiée et des résultats de l'alignement ;
    - dans laquelle chacun des motifs de modèle de vêtements stockés dans la base de données de motifs de modèle de vêtements contient au moins un des éléments suivants :
    -- un ensemble de points de contrôle qui définissent une relation entre la forme d'un vêtement et le corps portant ledit vêtement ;
    -- une description géométrique qui définit une relation entre la forme d'un vêtement et le corps portant ce vêtement.
  2. Le procédé selon la revendication 1,
    dans laquelle chacun des motifs de modèle de vêtements stockés dans la base de données de motifs de modèle de vêtements contient en outre au moins un des éléments suivants :
    - métadonnées associées à la forme d'un vêtement ;
    - métadonnées associées à un type de vêtement ;
    - métadonnées associées aux informations d'ajustement d'un vêtement.
  3. Le procédé selon la revendication 1 ou 2,
    dans laquelle l'adaptation des formes identifiées comprend l'alignement des points de contrôle et/ou d'une description géométrique contenue dans le motif de modèle de vêtement avec les points correspondants et/ou une description géométrique de la forme de la pièce du vêtement et de la forme de la personne.
  4. Le procédé selon l'une des revendications 1 à 3,
    dans laquelle, si le premier type est déterminé, la détermination des données du modèle de vêtement comprend la séparation des données d'image de fond et des données d'image corporelle, qui montrent des parties de la personne qui ne sont pas couvertes par le vêtement, des données d'image d'entrée pour obtenir des données d'image de vêtement, la séparation étant basée sur les formes identifiées adaptées et sur une identification couleur des données d'image d'entrée.
  5. Le procédé selon la revendication 4,
    dans laquelle, si le premier type est déterminé, la détermination des données de modèle de vêtement comprend en outre l'identification de régions dans les données d'image de vêtement, qui sont occultées, et la substitution de ces régions identifiées par des données d'image correspondantes, l'identification et/ou la substitution étant basées sur au moins un motif de modèle de vêtement extrait de la base de données du motifs de modèle de vêtement.
  6. Le procédé selon l'une des revendications 1 à 5, dans lequel l'identification d'au moins un motif de modèle de vêtement correspondant comprend la détermination itérative d'une mesure de similarité entre le motif de modèle de vêtement respectif et les données d'image entrées et/ou la forme identifiée, et la sélection du motif de modèle de vêtement correspondant en fonction des mesures de similarité déterminées de manière itérative.
  7. Le procédé selon l'une des revendications 1 à 6,
    dans laquelle l'alignement de la forme identifiée comprend l'alignement de points de contrôle et/ou d'une description géométrique contenue dans le au moins un motif de modèle de vêtement correspondant avec des points correspondants et/ou une description géométrique de la forme de la pièce de vêtement.
  8. Le procédé selon l'une des revendications 1 à 7,
    dans laquelle, si le second type est déterminé, la détermination des données du modèle de vêtement comprend l'obtention de données d'image de vêtement associées au morceau de vêtement à partir des données d'image d'entrée basées sur les formes identifiées alignées, et comprend en outre l'identification d'au moins une région dans les données d'image de vêtement qui ne serait pas visible, si le morceau de vêtement était porté par une personne, et l'exclusion de cette région identifiée des données d'image de vêtement et des données du modèle de vêtement.
  9. Le procédé selon la revendication 8,
    dans laquelle, si le second type est déterminé, l'identification d'au moins une région comprend la détermination de gradients d'image dans les données d'image du vêtement, la comparaison des gradients d'image à un ensemble de formes géométriques pour obtenir une quantité correspondante pour chacune des formes géométriques, la sélection d'une des formes géométriques basée sur les quantités correspondantes et la définition de la au moins une région basée sur la forme géométrique sélectionnée.
  10. Le procédé selon l'une des revendications 1 à 9,
    dans laquelle la détermination des données de modèle de vêtement comprend en outre, si la pièce de vêtement comprend une manche ou une jambe de pantalon, l'identification d'un premier et d'un second point le long de la manche ou de la jambe de pantalon, respectivement, la détermination de gradients d'image dans les données d'image d'entrée, la comparaison des gradients d'image avec un ensemble de chemins d'interconnexion entre le premier et le second point pour atteindre une quantité correspondante pour chacun des chemins d'interconnexion, et la sélection d'un des chemins d'interconnexion basés sur les quantités correspondantes à utiliser comme informations de séparation dans les données du modèle de vêtement.
  11. Le procédé selon l'une des revendications 1 à 10, dans laquelle les données du modèle de vêtement sont générées de telle sorte qu'elles contiennent des informations de profondeur et/ou des informations tridimensionnelles.
  12. Le procédé selon l'une des revendications 1 à 11, dans laquelle la détermination du type de condition d'usure est effectuée sur la base d'au moins un des éléments suivants :
    - la détection des visages ;
    - la détection du corps ;
    - la détection des parties du corps ;
    - détection des zones cutanées ;
    - détection des poils ;
    - la reconnaissance du vêtement ;
    - un état d'usure indiqué dans les métadonnées constituées par les données d'image d'entrée.
  13. Le procédé selon l'une des revendications 1 à 12,
    dans laquelle la retrouvant d'un motif de modèle de vêtement à partir de la base de données du motifs de modèle de vêtement est basée sur au moins un des éléments suivants :
    - un type de vêtement indiqué dans les métadonnées constituées par les données d'image d'entrée ;
    - une condition de prise de vue indiquée dans les métadonnées constituées par les données d'image d'entrée ;
    - un angle de prise de vue indiqué dans les métadonnées constituées par les données d'image d'entrée.
  14. Système (700) pour générer des données de modèle de vêtement représentatives d'une pièce de vêtement, le système comprenant un processeur (760) qui est configuré pour
    - traiter les données d'image d'entrée contenant une vue du vêtement ;
    - déterminer un type d'état de port à partir des données d'image d'entrée comme étant au moins l'un d'un premier type, où le vêtement est porté par une personne, et d'un second type, où le vêtement n'est pas porté ;
    - si le premier type est déterminé,
    -- identifier une forme de la pièce de vêtement et une forme de la personne portant la pièce de vêtement dans les données d'image d'entrée en utilisant une approche de modélisation de contour active basée sur un modèle de corps prédéfini, dans lequel l'approche de modélisation de contour active est initialisée avec un détecteur de visage et le modèle de corps prédéfini, qui est notamment un modèle statistique du corps ;
    -- adapter la forme identifiée de la pièce de vêtement et la forme identifiée de la personne, à partir d'un motif de modèle de vêtement extrait d'une base de données de motifs de modèle de vêtements ; et
    -- déterminer les données du modèle de vêtement à partir des données d'image d'entrée en se basant sur les formes identifiées adaptées ; et
    - si le deuxième type est déterminé,
    -- identifier une forme du vêtement dans les données de l'image d'entrée ;
    -- comparer de façon itérative les données d'image d'entrée avec un motif de modèle de vêtement respectif extrait de la base de données du motifs de modèle de vêtement pour identifier au moins un modèle de vêtement correspondant ;
    -- aligner la forme identifiée avec une forme d'au moins un motif de modèle de vêtement correspondant ; et
    -- déterminer les données du modèle de vêtement à partir des données d'image d'entrée en fonction de la forme identifiée et des résultats de l'alignement ;
    - dans laquelle chacun des motifs de modèle de vêtements stockés dans la base de données de motifs de modèle de vêtements contient au moins un des éléments suivants :
    -- un ensemble de points de contrôle qui définissent une relation entre la forme d'un vêtement et le corps portant ledit vêtement ;
    -- une description géométrique qui définit une relation entre la forme d'un vêtement et le corps portant ce vêtement.
  15. Produit de programme d'ordinateur comprenant un code de programme pour exécuter le procédé selon l'une des revendications 1 à 13, lorsque le produit de programme d'ordinateur fonctionne sur un ordinateur.
EP14199802.1A 2014-12-22 2014-12-22 Procédé et système de génération de données de modèle de vêtement Active EP3038053B1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
ES14199802T ES2765277T3 (es) 2014-12-22 2014-12-22 Método y sistema para generar datos de modelo de prenda
EP14199802.1A EP3038053B1 (fr) 2014-12-22 2014-12-22 Procédé et système de génération de données de modèle de vêtement
PCT/EP2015/079633 WO2016102228A1 (fr) 2014-12-22 2015-12-14 Procédé et système de génération de données de modèle de vêtement
US15/535,942 US10380794B2 (en) 2014-12-22 2015-12-14 Method and system for generating garment model data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP14199802.1A EP3038053B1 (fr) 2014-12-22 2014-12-22 Procédé et système de génération de données de modèle de vêtement

Publications (2)

Publication Number Publication Date
EP3038053A1 EP3038053A1 (fr) 2016-06-29
EP3038053B1 true EP3038053B1 (fr) 2019-11-06

Family

ID=52282502

Family Applications (1)

Application Number Title Priority Date Filing Date
EP14199802.1A Active EP3038053B1 (fr) 2014-12-22 2014-12-22 Procédé et système de génération de données de modèle de vêtement

Country Status (4)

Country Link
US (1) US10380794B2 (fr)
EP (1) EP3038053B1 (fr)
ES (1) ES2765277T3 (fr)
WO (1) WO2016102228A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4089641A1 (fr) 2021-05-12 2022-11-16 Reactive Reality AG Procédé de génération d'un avatar 3d, procédé de génération d'une image 2d en perspective à partir d'un avatar 3d et produit de programme informatique correspondant

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103927724B (zh) * 2014-04-30 2016-05-18 北京京东尚科信息技术有限公司 一种处理上衣图像的方法和装置
RU2551731C1 (ru) * 2014-07-02 2015-05-27 Константин Александрович Караваев Способ виртуального подбора одежды
US20220364356A1 (en) * 2014-07-11 2022-11-17 Robert William Pollack Systems, methods and machine readable programs for measuring, recording, and accessing data for improved selection of clothing
US10248993B2 (en) * 2015-03-25 2019-04-02 Optitex Ltd. Systems and methods for generating photo-realistic images of virtual garments overlaid on visual images of photographic subjects
US9984550B2 (en) * 2016-05-24 2018-05-29 International Business Machines Corporation Smart garment that communicates at least one parameter to a receiver
WO2018011649A1 (fr) * 2016-07-14 2018-01-18 Moda-Match Ltd. Adaptation d'articles vestimentaires à des images humaines
WO2018048902A1 (fr) * 2016-09-06 2018-03-15 Platform Orthopedic Solutions Inc Système, plate-forme, dispositif et procédé pour achats personnalisés
US20180160777A1 (en) 2016-12-14 2018-06-14 Black Brass, Inc. Foot measuring and sizing application
JP7225099B2 (ja) 2017-01-06 2023-02-20 ナイキ イノベイト シーブイ 自動ショッピングアシスタントを使用したパーソナライズショッピングのためのシステム、プラットフォームおよび方法
WO2019005986A1 (fr) 2017-06-27 2019-01-03 Nike Innovate C.V. Système, plateforme et procédé d'achat personnalisé à l'aide d'un assistant d'achat automatisé
US10546433B2 (en) * 2017-08-03 2020-01-28 The University Of North Carolina At Chapel Hill Methods, systems, and computer readable media for modeling garments using single view images
CN112262363A (zh) * 2018-02-27 2021-01-22 利惠商业有限公司 激光整理设计工具
US11738516B2 (en) * 2018-03-14 2023-08-29 Hewlett-Packard Development Company, L.P. Three dimensional model categories
US20190350287A1 (en) * 2018-05-18 2019-11-21 Meghan Litchfield Method of custom tailoring apparel at scale
CN109166172B (zh) * 2018-08-28 2023-04-07 深圳市维冠视界科技股份有限公司 服装模型的构建方法、装置、服务器和存储介质
EP3867855A4 (fr) 2018-10-19 2021-12-15 Perfitly, LLC. Plate-forme ar/vr perfitly
CN114667530A (zh) 2019-08-29 2022-06-24 利惠商业有限公司 具有服装和精加工的虚拟预览的数字陈列室
EP3798990B1 (fr) * 2019-09-30 2022-11-02 Reactive Reality AG Procédé et produit-programme d'ordinateur pour traiter des données de modèle d'un ensemble de vêtements
EP4158593A1 (fr) 2020-05-29 2023-04-05 NIKE Innovate C.V. Systèmes et procédés de traitement d'images capturées
US20220129973A1 (en) * 2020-10-22 2022-04-28 Adobe Inc. Image Modification to Generate Ghost Mannequin Effect in Image Content
US11983854B2 (en) * 2020-11-10 2024-05-14 Adobe Inc. Denoising images rendered using Monte Carlo renderings
KR102624995B1 (ko) * 2021-03-26 2024-01-15 엔에이치엔클라우드 주식회사 딥러닝 기반의 복수의 의류 가상착용 방법 및 그 시스템
JP2024008557A (ja) * 2022-07-08 2024-01-19 株式会社Ｎｔｔデータ 画像処理装置、画像処理方法、及びプログラム

Family Cites Families (135)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4539585A (en) 1981-07-10 1985-09-03 Spackova Daniela S Previewer
US4621012A (en) 1984-11-15 1986-11-04 Gunter Pusch Camouflage net having a semiconductive layer
JPH0696100A (ja) 1992-09-09 1994-04-08 Mitsubishi Electric Corp 遠隔取引システム
US5530652A (en) 1993-08-11 1996-06-25 Levi Strauss & Co. Automatic garment inspection and measurement system
US5680528A (en) 1994-05-24 1997-10-21 Korszun; Henry A. Digital dressing room
JP3543395B2 (ja) 1994-11-17 2004-07-14 株式会社日立製作所 サービス提供および利用方法
US6182871B1 (en) 1995-01-19 2001-02-06 Peter Ar-Fu Lam Personalized garment coordination apparatus
EP1848171A1 (fr) 1995-07-12 2007-10-24 NEC Corporation Procédé et dispositif pour modulation d'amplitude en quadrature à plusieurs niveaux
US5850222A (en) 1995-09-13 1998-12-15 Pixel Dust, Inc. Method and system for displaying a graphic image of a person modeling a garment
US5937081A (en) 1996-04-10 1999-08-10 O'brill; Michael R. Image composition system and method of using same
US5930769A (en) 1996-10-07 1999-07-27 Rose; Andrea System and method for fashion shopping
US6144388A (en) 1998-03-06 2000-11-07 Bornstein; Raanan Process for displaying articles of clothing on an image of a person
US6965873B1 (en) 1998-04-16 2005-11-15 Digimarc Corporation Electronic commerce using optical input device
US6307568B1 (en) 1998-10-28 2001-10-23 Imaginarix Ltd. Virtual dressing over the internet
US6415199B1 (en) 1999-02-25 2002-07-02 E-Z Max Apparel Systems, Inc. Method and apparatus for preparing custom-fitted clothing
US7062454B1 (en) 1999-05-06 2006-06-13 Jarbridge, Inc. Previewing system and method
US6404426B1 (en) 1999-06-11 2002-06-11 Zenimax Media, Inc. Method and system for a computer-rendered three-dimensional mannequin
US7328177B1 (en) 1999-07-20 2008-02-05 Catherine Lin-Hendel System and method for interactive, computer assisted personalization of on-line merchandise purchases
US6903756B1 (en) 1999-10-14 2005-06-07 Jarbridge, Inc. Merged images viewed via a virtual storage closet
US7917397B1 (en) 1999-10-14 2011-03-29 Jarbridge, Inc. Merging private images for gifting
US7418407B2 (en) 1999-10-14 2008-08-26 Jarbridge, Inc. Method for electronic gifting using merging images
DE10083644D2 (de) 1999-11-24 2002-10-31 Nico J Meyden Verfahren zur Auswahl und Anpassung eines Produktes an die Körpermasse eines Konsumenten
WO2001045029A2 (fr) 1999-12-10 2001-06-21 Lennon Jerry W Système de saisie d'image des clients et son utilisation dans un système de vente au détail
WO2001052140A1 (fr) 1999-12-21 2001-07-19 Jeff Silverman Systeme permettant de prevoir ou de determiner si un vetement est adapte a un client
GB9930448D0 (en) 1999-12-22 2000-02-16 Treleaven Philip C System and method for visualing personal appearance
US20010042029A1 (en) 2000-02-01 2001-11-15 Galvez Julian M. Own-likeness virtual model
US7149665B2 (en) 2000-04-03 2006-12-12 Browzwear International Ltd System and method for simulation of virtual wear articles on virtual models
AU2001245296A1 (en) 2000-04-03 2001-10-15 Browzwear International Ltd. System and method for virtual shopping of wear articles
US6968075B1 (en) 2000-05-09 2005-11-22 Chang Kurt C System and method for three-dimensional shape and size measurement
US6546309B1 (en) 2000-06-29 2003-04-08 Kinney & Lange, P.A. Virtual fitting room
US6901379B1 (en) 2000-07-07 2005-05-31 4-D Networks, Inc. Online shopping with virtual modeling and peer review
US20020024517A1 (en) 2000-07-14 2002-02-28 Komatsu Ltd. Apparatus and method for three-dimensional image production and presenting real objects in virtual three-dimensional space
US6661433B1 (en) 2000-11-03 2003-12-09 Gateway, Inc. Portable wardrobe previewing device
JP2002207802A (ja) 2000-12-19 2002-07-26 Shima Seiki Mfg Ltd アパレル製品販売支援方法および装置ならびに試着室
US6665577B2 (en) 2000-12-20 2003-12-16 My Virtual Model Inc. System, method and article of manufacture for automated fit and size predictions
GB0101371D0 (en) 2001-01-19 2001-03-07 Virtual Mirrors Ltd Production and visualisation of garments
US7194428B2 (en) 2001-03-02 2007-03-20 Accenture Global Services Gmbh Online wardrobe
WO2001073688A2 (fr) 2001-03-28 2001-10-04 Robert Massen Procedes et systeme de traitement de donnees permettant de simplifier le commerce electronique de produits devant etre adaptes a la forme d'un objet
US6530726B2 (en) 2001-04-04 2003-03-11 Kennametal Inc. Cutting insert having improved cutting
US20020188372A1 (en) 2001-05-10 2002-12-12 Lane Kenneth M. Method and system for computer aided garment selection
US6711455B1 (en) 2001-07-20 2004-03-23 Archetype Solutions, Inc. Method for custom fitting of apparel
GB0120039D0 (en) 2001-08-16 2001-10-10 Univ London Method for dressing and animating dressed beings
US20030050864A1 (en) 2001-09-13 2003-03-13 Koninklijke Philips Electronics N.V. On-line method for aiding a customer in the purchase of clothes
US7479956B2 (en) 2001-10-19 2009-01-20 Unique Solutions Design Ltd. Method of virtual garment fitting, selection, and processing
US7953648B2 (en) 2001-11-26 2011-05-31 Vock Curtis A System and methods for generating virtual clothing experiences
US7386429B1 (en) 2001-12-07 2008-06-10 Iwao Fujisaki Wrinkle simulation software
US20030110099A1 (en) 2001-12-11 2003-06-12 Philips Electronics North America Corporation Virtual wearing of clothes
FR2837593B1 (fr) 2002-03-22 2004-05-28 Kenneth Kuk Kei Wang Procede et dispositif de visualisation, d'archivage et de transmission sur un reseau d'ordinateurs d'un modele de vetement
ATE375570T1 (de) 2002-06-10 2007-10-15 Accenture Global Services Gmbh Interaktiver anproberaum
US7194327B2 (en) 2002-07-12 2007-03-20 Peter Ar-Fu Lam Body profile coding method and apparatus useful for assisting users to select wearing apparel
JP2004086803A (ja) 2002-08-29 2004-03-18 Fujitsu Ltd 仮想試着のための情報処理方法及び装置
WO2004079555A2 (fr) 2003-03-06 2004-09-16 Archetype Solutions, Inc. Procede de table de recherche destine a l'adaptation personnalisee d'un vetement
US20040227752A1 (en) 2003-05-12 2004-11-18 Mccartha Bland Apparatus, system, and method for generating a three-dimensional model to represent a user for fitting garments
US6810300B1 (en) 2003-05-22 2004-10-26 Kimberly-Clark Worldwide, Inc. Method of designing a product worn on a body in a virtual environment
US8229799B2 (en) 2003-09-27 2012-07-24 Tara Chand Singhal System and method for simulating apparel fit while maintaining customer privacy on a global computer network
US20050131776A1 (en) 2003-12-15 2005-06-16 Eastman Kodak Company Virtual shopper device
JP4533643B2 (ja) 2004-02-26 2010-09-01 株式会社島精機製作所 人体モデルへのニットガーメントの着装シミュレーション方法とその装置、並びにそのプログラム
US20050234782A1 (en) 2004-04-14 2005-10-20 Schackne Raney J Clothing and model image generation, combination, display, and selection
FR2870618B1 (fr) 2004-05-21 2007-04-06 Kenneth Kuk Kei Wang Procede d'acquisition et de gestion sur un reseau d'ordinateurs de donnees morphologiques de personnes, et dispositif adapte a la mise en oeuvre dudit procede
US8660902B2 (en) 2004-07-23 2014-02-25 Lori Coulter, Llc Methods and systems for selling apparel
US7421306B2 (en) 2004-09-16 2008-09-02 Sanghati, Llc Apparel size service
US7212665B2 (en) 2004-11-05 2007-05-01 Honda Motor Co. Human pose estimation with data driven belief propagation
KR100511210B1 (ko) 2004-12-27 2005-08-30 주식회사지앤지커머스 의사 쓰리디 이미지 생성기법을 토대로 한 이용자 적응인공지능 토탈 코디네이션 방법과, 이를 이용한 서비스사업방법
US20060149638A1 (en) 2005-01-06 2006-07-06 Allen Anita L Electronic personalized clothing makeover assistant
JP4473754B2 (ja) 2005-03-11 2010-06-02 株式会社東芝 仮想試着装置
US7617016B2 (en) 2005-04-27 2009-11-10 Myshape, Inc. Computer system for rule-based clothing matching and filtering considering fit rules and fashion rules
US7398133B2 (en) 2005-04-27 2008-07-08 Myshape, Inc. Matching the fit of individual garments to individual consumers
EP1949253A4 (fr) 2005-09-30 2011-01-26 Sk C&C Co Ltd Systeme de service d'album numerique permettant de montrer des elements de mode crees par un utilisateur et procede pour le faire fonctionner
US20080249897A1 (en) 2005-09-30 2008-10-09 Sk C&C Co. Ltd Electronic Commerce System for the Digital Fashion Using an Avatar Based on a User and Method for Operating the Same
ES2279708B1 (es) 2005-11-15 2008-09-16 Reyes Infografica, S.L. Metodo de generacion y utilizacion de un probador virtual de prendas de vestir, y sistema.
US7487116B2 (en) 2005-12-01 2009-02-03 International Business Machines Corporation Consumer representation rendering with selected merchandise
US8370360B2 (en) 2005-12-31 2013-02-05 G & G Commerce Ltd. Merchandise recommending system and method thereof
US20080082395A1 (en) 2006-08-17 2008-04-03 Shulman Olivia M Virtual closet
US20080071559A1 (en) 2006-09-19 2008-03-20 Juha Arrasvuori Augmented reality assisted shopping
TW200828043A (en) 2006-12-29 2008-07-01 Cheng-Hsien Yang Terminal try-on simulation system and operating and applying method thereof
US20080163054A1 (en) 2006-12-30 2008-07-03 Pieper Christopher M Tools for product development comprising collections of avatars and virtual reality business models for avatar use
DE202007008176U1 (de) 2007-06-12 2007-08-23 Kühn, Dieter Virtuelle Ankleide
US20090018926A1 (en) 2007-07-13 2009-01-15 Divina Buehlman Web-based virtual clothing coordinator including personal mannequin with customer-directed measurements, image modification and clothing
US8174521B2 (en) 2007-10-26 2012-05-08 Zazzle.Com Product modeling system and method
US8036416B2 (en) 2007-11-06 2011-10-11 Palo Alto Research Center Incorporated Method and apparatus for augmenting a mirror with information related to the mirrored contents and motion
US8068676B2 (en) 2007-11-07 2011-11-29 Palo Alto Research Center Incorporated Intelligent fashion exploration based on clothes recognition
US7925081B2 (en) 2007-12-12 2011-04-12 Fuji Xerox Co., Ltd. Systems and methods for human body pose estimation
CN101933021B (zh) 2008-02-18 2012-10-17 株式会社岛精机制作所 穿着模拟装置和模拟方法
US8095426B2 (en) 2008-02-19 2012-01-10 Size Me Up, Inc. System and method for comparative sizing between a well-fitting source item and a target item
GB2458388A (en) 2008-03-21 2009-09-23 Dressbot Inc A collaborative online shopping environment, virtual mall, store, etc. in which payments may be shared, products recommended and users modelled.
US8386486B2 (en) 2008-07-02 2013-02-26 Palo Alto Research Center Incorporated Method for facilitating social networking based on fashion-related information
AU2009281762A1 (en) 2008-08-15 2010-02-18 Brown University Method and apparatus for estimating body shape
US20100049633A1 (en) 2008-08-22 2010-02-25 Myshape, Inc. System and method to identify and visually distinguish personally relevant items
US20110078055A1 (en) 2008-09-05 2011-03-31 Claude Faribault Methods and systems for facilitating selecting and/or purchasing of items
CA2737025C (fr) 2008-09-27 2012-09-04 Jina Pharmaceuticals, Inc. Preparations pharmaceutiques a base de lipide(s) a usage oral et topique, leurs compositions, procedes et utilisations
CA2681697A1 (fr) 2008-10-09 2010-04-09 Retail Royalty Company Methodes et systemes d'achats en ligne
US20100191770A1 (en) 2009-01-27 2010-07-29 Apple Inc. Systems and methods for providing a virtual fashion closet
WO2010096878A1 (fr) 2009-02-27 2010-09-02 Clonnequin Pty Ltd Système et procédé de facilitation d'achat en ligne de vêtements
US8700477B2 (en) 2009-05-26 2014-04-15 Embodee Corp. Garment fit portrayal system and method
US8364561B2 (en) 2009-05-26 2013-01-29 Embodee Corp. Garment digitization system and method
US8275590B2 (en) 2009-08-12 2012-09-25 Zugara, Inc. Providing a simulation of wearing items such as garments and/or accessories
GB2473503B (en) 2009-09-15 2015-02-11 Metail Ltd System and method for image processing
CN101736921B (zh) 2009-09-25 2011-06-08 东莞市新雷神仿真控制有限公司 电子衣柜
WO2011050205A1 (fr) 2009-10-23 2011-04-28 True Fit Corp. Système et procédé pour communiquer à des consommateurs des informations personnalisées concernant des produits
US8682738B2 (en) 2009-10-29 2014-03-25 At&T Intellectual Property I, Lp System and method for using a digital inventory of clothing
US8674989B1 (en) 2009-12-17 2014-03-18 Google Inc. System and method for rendering photorealistic images of clothing and apparel
US8116896B2 (en) 2009-12-22 2012-02-14 Ko Young-A Method for creating panels for a garment
US20110157218A1 (en) 2009-12-29 2011-06-30 Ptucha Raymond W Method for interactive display
US8390648B2 (en) 2009-12-29 2013-03-05 Eastman Kodak Company Display system for personalized consumer goods
US8090465B2 (en) 2010-03-04 2012-01-03 Belinda Luna Zeng Fashion design method, system and apparatus
US8429025B2 (en) 2010-03-17 2013-04-23 Amanda Fries Method, medium, and system of ascertaining garment size of a particular garment type for a consumer
US9959453B2 (en) 2010-03-28 2018-05-01 AR (ES) Technologies Ltd. Methods and systems for three-dimensional rendering of a virtual augmented replica of a product image merged with a model image of a human-body feature
US9646340B2 (en) 2010-04-01 2017-05-09 Microsoft Technology Licensing, Llc Avatar-based virtual dressing room
US8655053B1 (en) * 2010-05-31 2014-02-18 Andrew S Hansen Body modeling and garment fitting using an electronic device
US20110298897A1 (en) 2010-06-08 2011-12-08 Iva Sareen System and method for 3d virtual try-on of apparel on an avatar
WO2011156474A2 (fr) 2010-06-10 2011-12-15 Brown University Modèle paramétré de forme humaine articulée en 2 dimensions
US8321301B2 (en) 2010-07-20 2012-11-27 Sony Corporation Method and system for clothing shopping using an image of a shopper
WO2012016052A1 (fr) 2010-07-28 2012-02-02 True Fit Corporation Recommandation de taille par inférence collaborative
US10127606B2 (en) 2010-10-13 2018-11-13 Ebay Inc. Augmented reality system and method for visualizing an item
US8711175B2 (en) 2010-11-24 2014-04-29 Modiface Inc. Method and system for simulating superimposition of a non-linearly stretchable object upon a base object using representative images
TWI507916B (zh) 2010-12-24 2015-11-11 Nat Univ Tsing Hua 運用擴增實境之衣物試穿方法及系統
GB201102794D0 (en) 2011-02-17 2011-03-30 Metail Ltd Online retail system
US20120287122A1 (en) 2011-05-09 2012-11-15 Telibrahma Convergent Communications Pvt. Ltd. Virtual apparel fitting system and method
US9241184B2 (en) 2011-06-01 2016-01-19 At&T Intellectual Property I, L.P. Clothing visualization
US20130083065A1 (en) 2011-08-02 2013-04-04 Jessica Schulze Fit prediction on three-dimensional virtual model
TW201310369A (zh) 2011-08-25 2013-03-01 Hon Hai Prec Ind Co Ltd 虛擬試衣系統及方法
US20130054425A1 (en) 2011-08-29 2013-02-28 Francesco Alexander Portelos Web-based system permitting a customer to shop online for clothes with their own picture
JP5845830B2 (ja) 2011-11-09 2016-01-20 ソニー株式会社 情報処理装置、表示制御方法、およびプログラム
US8606645B1 (en) 2012-02-02 2013-12-10 SeeMore Interactive, Inc. Method, medium, and system for an augmented reality retail application
US20130219434A1 (en) 2012-02-20 2013-08-22 Sony Corporation 3d body scan input to tv for virtual fitting of apparel presented on retail store tv channel
US20150058083A1 (en) 2012-03-15 2015-02-26 Isabel Herrera System for personalized fashion services
US20140108208A1 (en) 2012-03-26 2014-04-17 Tintoria Piana U.S., Inc. Personalized virtual shopping assistant
US9147207B2 (en) * 2012-07-09 2015-09-29 Stylewhile Oy System and method for generating image data for on-line shopping
US9799064B2 (en) 2012-08-03 2017-10-24 Eyefitu Ag Garment fitting system and method
US9898742B2 (en) * 2012-08-03 2018-02-20 Ebay Inc. Virtual dressing room
WO2014028714A2 (fr) 2012-08-15 2014-02-20 Fashpose, Llc Système et procédé de simulation de modélisation de vêtement
US9449343B2 (en) 2012-10-05 2016-09-20 Sap Se Augmented-reality shopping using a networked mobile device
SG10201703852XA (en) 2012-11-12 2017-06-29 Singapore Univ Of Tech And Design Clothing matching system and method
SG11201503974SA (en) 2012-11-22 2015-06-29 Agency Science Tech & Res Method, apparatus and system for virtual clothes modelling
US10637779B1 (en) 2018-10-16 2020-04-28 Oracle International Corporation Methods, systems, and computer readable media for diameter signaling message external identifier address resolution and routing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
None *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4089641A1 (fr) 2021-05-12 2022-11-16 Reactive Reality AG Procédé de génération d'un avatar 3d, procédé de génération d'une image 2d en perspective à partir d'un avatar 3d et produit de programme informatique correspondant
WO2022238083A1 (fr) 2021-05-12 2022-11-17 Reactive Reality Ag Procédé de génération d'un avatar 3d, procédé de génération d'une image 2d en perspective à partir d'un avatar 3d et produit programme d'ordinateur associé

Also Published As

Publication number Publication date
US20170372515A1 (en) 2017-12-28
WO2016102228A1 (fr) 2016-06-30
ES2765277T3 (es) 2020-06-08
EP3038053A1 (fr) 2016-06-29
US10380794B2 (en) 2019-08-13

Similar Documents

Publication Publication Date Title
US10380794B2 (en) Method and system for generating garment model data
EP3479296B1 (fr) Système d'habillage virtuel utilisant un traitement d'image, un apprentissage automatique et une vision artificielle
US12062114B2 (en) Method, system, and device of virtual dressing utilizing image processing, machine learning, and computer vision
CN110662484B (zh) 用于全身测量结果提取的系统和方法
US10067500B2 (en) Generating of 3D-printed custom wearables
US10991067B2 (en) Virtual presentations without transformation-induced distortion of shape-sensitive areas
CN105404392B (zh) 基于单目摄像头的虚拟穿戴方法及系统
US8036416B2 (en) Method and apparatus for augmenting a mirror with information related to the mirrored contents and motion
JP2019510297A (ja) ユーザの真実の人体モデルへの仮想的な試着
JP2017531950A (ja) 撮影テンプレートデータベースを構築し、且つ撮影推薦情報を提供するための方法及び装置
JP5439787B2 (ja) カメラ装置
WO2014081394A1 (fr) Procédé, appareil et système pour la modélisation virtuelle de vêtements
KR20240125620A (ko) 실시간 상체 의복 교환
EP3998571A1 (fr) Procédés de capture d'images et de fabrication de vêtements
US11386615B2 (en) Creating a custom three-dimensional body shape model
US9953242B1 (en) Identifying items in images using regions-of-interest
Silva et al. Automatic system to identify and manage garments for blind people
KR101321022B1 (ko) 증강 현실 구현 방법 및 증강 현실을 구현하는 컴퓨팅 장치 및 시스템
Kowerko et al. Evaluation of CNN-based algorithms for human pose analysis of persons in red carpet scenarios
JP2021140405A (ja) 画像検索装置、画像検索方法及び画像検索プログラム

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20161222

RBV Designated contracting states (corrected)

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: REACTIVE REALITY GMBH

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602014056228

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: G06T0007000000

Ipc: G06T0007330000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 7/33 20170101AFI20190619BHEP

Ipc: G06T 7/149 20170101ALI20190619BHEP

Ipc: G06T 7/12 20170101ALI20190619BHEP

Ipc: G06T 17/10 20060101ALI20190619BHEP

Ipc: G06T 17/00 20060101ALI20190619BHEP

Ipc: G06T 7/11 20170101ALI20190619BHEP

INTG Intention to grant announced

Effective date: 20190723

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

Ref country code: AT

Ref legal event code: REF

Ref document number: 1199813

Country of ref document: AT

Kind code of ref document: T

Effective date: 20191115

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602014056228

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: NV

Representative=s name: PATENTANWALTSKANZLEI NUECKEL, CH

RAP2 Party data changed (patent owner data changed or rights of a patent transferred)

Owner name: REACTIVE REALITY GMBH

REG Reference to a national code

Ref country code: SE

Ref legal event code: TRGR

REG Reference to a national code

Ref country code: CH

Ref legal event code: PCOW

Free format text: NEW ADDRESS: WALTENDORFER HAUPTSTRASSE 32A, 8010 GRAZ (AT)

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20191106

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200306

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200206

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200206

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200207

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20200306

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

REG Reference to a national code

Ref country code: ES

Ref legal event code: FG2A

Ref document number: 2765277

Country of ref document: ES

Kind code of ref document: T3

Effective date: 20200608

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602014056228

Country of ref document: DE

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1199813

Country of ref document: AT

Kind code of ref document: T

Effective date: 20191106

REG Reference to a national code

Ref country code: BE

Ref legal event code: MM

Effective date: 20191231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed

Effective date: 20200807

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20191222

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20191222

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20191231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO

Effective date: 20141222

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20191106

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20231220

Year of fee payment: 10

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: SE

Payment date: 20231219

Year of fee payment: 10

Ref country code: FR

Payment date: 20231219

Year of fee payment: 10

Ref country code: DE

Payment date: 20231220

Year of fee payment: 10

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: ES

Payment date: 20240118

Year of fee payment: 10

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: CH

Payment date: 20240110

Year of fee payment: 10

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: IT

Payment date: 20231229

Year of fee payment: 10